# US 11,908,586 B2 · Systems and methods for extracting dates associated with a patient condition

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,908,586 B2
- Document ID: US11908586B2
- Status: Granted
- Kind: B2
- Application number: 17/345,448
- Filed: 2021-06-11
- Published: 2021-12-16
- Granted: 2024-02-20
- Earliest claimed: 2020-06-12
- Assignees: Flatiron Health, Inc.
- Applicants: Flatiron Health, Inc.
- Inventors: James Gippetti; Sharang Phadke; Guy Amster; Nisha Singh; Suganya Sridharma; Melissa Estevez; John Ritten; Sankeerth Garapati; Aaron Cohen
- Web page: https://patentgrep.com/patent/US11908586B2

## CPC

- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G06F 16/33: Querying
- G06N 20/00: Machine learning
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 15/00: ICT specially adapted for medical reports, e.g. generation or transmission thereof
- G16H 40/20: for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A model-assisted system for extracting patient information. A processor may be programmed to access a database storing one or more medical records associated with a patient and determine, using a first machine learning model and based on unstructured information included in the one or more medical records, whether the patient is associated with a condition. The processor may further be programmed to identify a date associated with the patient and determine, using a second machine learning model and based on the unstructured information, whether the patient is associated with the condition relative to the date. The processor may generate an output indicating whether the patient is associated with the condition and whether the patient is associated with the condition relative to the date.

## Claims

### Claim 1

A model-assisted system for extracting patient information, the system comprising:
at least one processor programmed to:
access a database storing a plurality of medical records associated with a plurality of patients;
input unstructured information included in the plurality of medical records into a first machine learning model, the first machine learning model being trained using first training data to identify patients associated with a condition;
identify, based on a first output from the first machine learning model, a subset of the plurality of patients, the subset of the plurality of patients being associated with the condition;
identify, based on an input by a user through a user interface, a date associated with a patient of the subset of the plurality of patients;
identify, within the plurality of medical records, one or more documents associated with the patient and having a timestamp prior to a cutoff date such that documents including one or more dates expressed in relative terms are excluded from the identified one or more documents, the cutoff date being based on a predetermined buffer period before or after the date;
input unstructured information included in the one or more documents into a second machine learning model, the second machine learning model being trained using second training data to indicate dates associated with the condition;
generate one or more pseudo-documents for input into the second machine learning model, the one or more pseudo-documents accounting for one or more dates within the unstructured information included in the one or more documents;
determine, based on a second output from the second machine learning model, whether the patient is associated with the condition relative to the date; and
generate an output indicating whether the patient is associated with the condition and whether the patient is associated with the condition relative to the date.

### Claim 2 (depends on 1)

The system of claim 1, wherein the condition includes a diagnosed metastatic site associated with the patient.

### Claim 3 (depends on 2)

The system of claim 2, wherein the diagnosed metastatic site includes a brain metastasis.

### Claim 4 (depends on 1)

The system of claim 1, wherein the condition includes a diagnosed condition of the patient.

### Claim 5 (depends on 1)

The system of claim 1, wherein determining whether the patient is associated with the condition includes determining whether the patient has been tested for the condition.

### Claim 6 (depends on 1)

The system of claim 1, wherein identifying the date includes identifying at least one of a start date or an end date for a line of treatment for the patient in association with the condition.

### Claim 7 (depends on 1)

The system of claim 1, wherein identifying the date includes identifying a plurality of dates and wherein determining whether the patient is associated with the condition includes determining whether the patient is associated with the condition relative to each of the plurality of dates.

### Claim 8 (depends on 7)

The system of claim 7, wherein the plurality of dates each include a start dates for a particular line of treatment for the patient in association with the condition.

### Claim 9 (depends on 1)

The system of claim 1, wherein the at least one processor is further programmed to:
determine, using the first machine learning model and based on the unstructured information included in the plurality of medical records, whether each of the plurality of patients is associated with the condition; and
determine, using the second machine learning model and based on the unstructured information, whether each of the subset of the plurality of patients is associated with the condition relative to the date; and
wherein the output identifies a group of the subset of the plurality of patients associated with the condition relative to the date.

### Claim 10 (depends on 1)

The system of claim 1, wherein the at least one processor is further programmed to transmit the output to at least one of a healthcare provider or a research entity.

### Claim 11

A computer-assisted method for extracting patient information, the method comprising:
accessing a database storing a plurality of medical records associated with a plurality of patients;
inputting unstructured information included in the plurality of medical records into a first machine learning model, the first machine learning model being trained using first training data to identify patients associated with a condition;
identifying, based on a first output from the first machine learning model, a subset of the plurality of patients, the subset of the plurality of patients being associated with the condition;
identifying, based on an input by a user through a user interface, a date associated with a patient of the subset of the plurality of patients;
identifying, within the plurality of medical records, one or more documents associated with the patient and having a timestamp prior to a cutoff date such that documents including one or more dates expressed in relative terms are excluded from the identified one or more documents, the cutoff date being based on a predetermined buffer period before or after the date;
inputting unstructured information included in the one or more documents into a second machine learning model, the second machine learning model being trained using second training data to indicate dates associated with the condition;
generating one or more pseudo-documents for input into the second machine learning model, the one or more pseudo-documents accounting for one or more dates within the unstructured information included in the one or more documents;
determining, based on a second output from the second machine learning model, whether the patient is associated with the condition relative to the date; and
generating an output indicating whether the patient is associated with the condition and whether the patient is associated with the condition relative to the date.

### Claim 12 (depends on 11)

The method of claim 11, wherein the condition includes a diagnosed metastatic site associated with the patient.

### Claim 13 (depends on 11)

The method of claim 11, wherein identifying the date includes identifying at least one of a start date or an end date for a line of treatment for the patient in association with the condition.

### Claim 14

A non-transitory computer-readable medium storing instructions executable by at least one processor to perform a method, the method comprising:
accessing a database storing a plurality of medical records associated with a plurality of patients;
inputting unstructured information included in the plurality of medical records into a first machine learning model, the first machine learning model being trained using first training data to identify patients associated with a condition;
identifying, based on a first output from the first machine learning model, a subset of the plurality of patients, the subset of the plurality of patients being associated with the condition;
identifying, based on an input by a user through a user interface, a date associated with a patient of the subset of the plurality of patients;
identifying, within the plurality of medical records, one or more documents associated with the patient and having a timestamp prior to a cutoff date such that documents including one or more dates expressed in relative terms are excluded from the identified one or more documents, the cutoff date being based on a predetermined buffer period before or after the date;
inputting unstructured information included in the one or more documents into a second machine learning model, the second machine learning model being trained using second training data to indicate dates associated with the condition;
generating one or more pseudo-documents for input into the second machine learning model, the one or more pseudo-documents accounting for one or more dates within the unstructured information included in the one or more documents;
determining, based on a second output from the second machine learning model, whether the patient is associated with the condition relative to the date; and
generating an output indicating whether the patient is associated with the condition and whether the patient is associated with the condition relative to the date.

### Claim 15 (depends on 1)

The system of claim 1, wherein the one or more pseudo-documents are each associated with a document date matching the one or more dates within the unstructured information included in the one or more documents.

### Claim 16 (depends on 1)

The system of claim 1, wherein the one or more pseudo-documents include information indicating a date as though text within the one or more pseudo-documents was written on the indicated date.